Reverse Scaling

Purpose of Reverse Scaling

In his presentation of scaling, Likert recommended constructing scales to balance the item wording and phrase approximately half the items in the reverse. The recommendation to use reverse scaling continues because many psychometricians believe that the inclusion of reverse coded items motivates participants to process items more carefully and prevents negative respondent behaviors such as response set, satisficing, and acquiescence. Response set is the tendency of participants to respond to the set of scale items rather than individual items. For example, a respondent may have a positive impression of an instructor being evaluated and simply respond to the entire set of items positively rather than processing the nuances of each item individually. The inclusion of an item worded in the opposite direction could encourage participants to read and process each item more carefully. Psychologists contend that people prefer to answer in agreement rather than disagreement; therefore, participants may acquiesce or simply agree with an item out of some form of social desirability. Furthermore, participants may also satisfice or agree [Page 844]with an item because doing so requires minimal cognitive effort. Therefore, reverse coded items are prescribed to force participants to process individual items more carefully and accommodate participants who wish to vary their responses and not always provide the same answer.

Coding and Scoring of Reverse Coded Items

For initial coding purposes, it is best to code reverse coded items in the same way that the traditional items are coded (i.e., strongly agree = 5, agree = 4, neutral = 3, disagree = 2, and strongly disagree = 1). However, once the data have been entered, the scores for all reverse coded items should be recoded to facilitate consistent interpretation of the data and must be recoded if items are to be combined to form scales. Suppose a scale contained four traditionally worded items and one reverse coded item. If a respondent strongly agreed with the construct measured by the scale, they should respond strongly agree to the four traditionally worded items and strongly disagree to the reverse coded item. Thus, the raw scale score for the respondent would be 21 (i.e., 5 + 5 + 5 + 5 + 1 = 21). This score of 21 is misleading because of the score of 1 for the reverse coded item. The score of 21, rather than 25, indicates less than strong agreement with the scale items. Therefore, the scores for all reverse coded items must be recoded. Researchers using any instrument must always search for reverse coded items that might be included in the instrument.

...